Instructions to use hydroxai/hydro-safe-llama2-7b-chat-peft-dpo with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use hydroxai/hydro-safe-llama2-7b-chat-peft-dpo with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="hydroxai/hydro-safe-llama2-7b-chat-peft-dpo")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("hydroxai/hydro-safe-llama2-7b-chat-peft-dpo")
model = AutoModelForCausalLM.from_pretrained("hydroxai/hydro-safe-llama2-7b-chat-peft-dpo", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use hydroxai/hydro-safe-llama2-7b-chat-peft-dpo with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "hydroxai/hydro-safe-llama2-7b-chat-peft-dpo"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "hydroxai/hydro-safe-llama2-7b-chat-peft-dpo",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/hydroxai/hydro-safe-llama2-7b-chat-peft-dpo

SGLang

How to use hydroxai/hydro-safe-llama2-7b-chat-peft-dpo with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "hydroxai/hydro-safe-llama2-7b-chat-peft-dpo" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "hydroxai/hydro-safe-llama2-7b-chat-peft-dpo",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "hydroxai/hydro-safe-llama2-7b-chat-peft-dpo" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "hydroxai/hydro-safe-llama2-7b-chat-peft-dpo",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use hydroxai/hydro-safe-llama2-7b-chat-peft-dpo with Docker Model Runner:
```
docker model run hf.co/hydroxai/hydro-safe-llama2-7b-chat-peft-dpo
```

Model Card for Model ID

Overview

This repository contains the model card for the 🤗 transformers model "hydroxai/hydro-safe-llama2-7b-chat-peft-dpo" that has been published on the Hub. The model card provides detailed information about its development, usage, risks, and more.

Model Details

Model Description

The "hydroxai/hydro-safe-llama2-7b-chat-peft-dpo" model is based on the llama2 architecture and has been fine-tuned using PEFT and DPO methods. It is specifically designed for chat applications with enhanced privacy and security features.

Security Enhancements

The model incorporates advanced security enhancements to protect user privacy and data integrity, including:

Implementation of robust data anonymization techniques during training and inference.
Integration of privacy-preserving protocols for secure data transmission and storage.
Regular audits and compliance checks to ensure adherence to privacy regulations and standards.
Mechanisms for user consent management and transparency in data handling practices.

These security measures ensure that the "hydroxai/hydro-safe-llama2-7b-chat-peft-dpo" model upholds high standards of privacy and security, making it suitable for deployment in sensitive conversational AI applications.

Downloads last month: 8

Safetensors

Model size

7B params

Tensor type

F16